Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The air inside the apartment was thick with the scent of stale coffee and unfulfilled dreams. He felt a profound sense of disconnection from everything, as though he were watching his life from behind a sheet of glass. He went to a bookstore, hoping for an escape, any escape. He browsed the shelves, his eyes scanning the titles, but nothing really captured his attention.

He pulled a well-worn copy of “Hamlet” from the shelf. As he flipped through the pages, a small packet of dried lavender fell out, along with a letter. The paper was thick, almost velvety, and the handwriting was elegant and precise. The letter spoke of a love that had ended too soon, of regrets and what-ifs. He closed the book and held the letter, feeling a strange tug at his heart.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

This story is one of 1,000 stories generated for the emotion listless. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 listless stories, after denoising with neutral dialogue baselines, produces the listless emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the listless vector is projected through the unembedding matrix.

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273